Python爬虫实战(一)：爬取豆瓣电影top250排名

先上代码

#coding=utf-8
import re
import urllib.request

def getHtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    html = html.decode('utf-8')
    return html

def getItem(html):
    reg = re.compile(r'.*?<span class="title">(.*?)</span>.*?<p class="">.*?(\d+).*?</p>.*?<span class="rating_num" property="v:average">(.*?)</span>.*?<span>(\d+)人评价',re.S)
    items = re.findall(reg,html)
    global index
    for index,item in enumerate(items,index+1):
        print (index,item)

     
if __name__=='__main__':
    index = 0
    for i in range(0,226,25):
        url  = "https://movie.douban.com/top250?start="
        url += str(i) + "&filter="
        html = getHtml(url)
        getItem(html)

    print ("\nOK!All OVER!")

#关于正则表达式的一些说明
#<span class="title">(.*?)</span>  获取电影名字
#<p class="">.*?(\d+) 获取电影上映年份
#<span class="rating_num" property="v:average">(.*?)</span> 获取评分
#</span>.*?<span>(\d+)人评价  获取评价人数   

如果想要代码看起来更优雅点，可以去掉

global index

index = 0

再将  index+1 改成1，只是不能按顺序统计了。

#coding=utf-8
import re
import urllib.request

def getHtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    html = html.decode('utf-8')
    return html

def getItem(html):
    reg = re.compile(r'.*?<span class="title">(.*?)</span>.*?<p class="">.*?(\d+).*?</p>.*?<span class="rating_num" property="v:average">(.*?)</span>.*?<span>(\d+)人评价',re.S)
    items = re.findall(reg,html)
    for index,item in enumerate(items,1):
        print (index,item)

     
if __name__=='__main__':
    for i in range(0,226,25):
        url  = "https://movie.douban.com/top250?start="
        url += str(i) + "&filter="
        html = getHtml(url)
        getItem(html)

    print ("\nOK!All OVER!")

#coding=utf-8
import re
import requests
from prettytable import PrettyTable
from colorama import init,Fore

def getHtml(url):  
    page = requests.get(url)  
    html = page.text  
    return html

def getItem(html):
    reg = re.compile(r'.*?<span class="title">(.*?)</span>.*?<p class="">.*?(\d+).*?</p>.*?<span class="rating_num" property="v:average">(.*?)</span>.*?<span>(\d+)人评价',re.S)
    items = re.findall(reg,html)
    return items

     
if __name__=='__main__':
    movie = []
    init(autoreset=True)
    table = PrettyTable([Fore.RED +"排名", "电影名",'上映年份','综合评分','评价人数'])
    for i in range(0,226,25):
        url  = "https://movie.douban.com/top250?start="
        url += str(i) + "&filter="
        html = getHtml(url)
        items = getItem(html)
        for item in items:
            movie.append(item)
    for index,item in enumerate(movie,1):
        if index % 4 == 0:
            color = Fore.RED
        elif index % 4 == 1:
            color = Fore.YELLOW
        elif index % 4 == 2:
            color = Fore.GREEN
        else:
            color = Fore.CYAN
        table.add_row([color + str(index),item[0],item[1],item[2],item[3]])
    print (table)